summaryrefslogtreecommitdiff
path: root/lib/Target/X86/X86SelectionDAGInfo.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'lib/Target/X86/X86SelectionDAGInfo.cpp')
-rw-r--r--lib/Target/X86/X86SelectionDAGInfo.cpp62
1 files changed, 38 insertions, 24 deletions
diff --git a/lib/Target/X86/X86SelectionDAGInfo.cpp b/lib/Target/X86/X86SelectionDAGInfo.cpp
index 9da8a18965ea6..1a72a0ba3a642 100644
--- a/lib/Target/X86/X86SelectionDAGInfo.cpp
+++ b/lib/Target/X86/X86SelectionDAGInfo.cpp
@@ -106,7 +106,6 @@ SDValue X86SelectionDAGInfo::EmitTargetCodeForMemset(
SDValue Count;
ConstantSDNode *ValC = dyn_cast<ConstantSDNode>(Src);
unsigned BytesLeft = 0;
- bool TwoRepStos = false;
if (ValC) {
unsigned ValReg;
uint64_t Val = ValC->getZExtValue() & 255;
@@ -163,20 +162,7 @@ SDValue X86SelectionDAGInfo::EmitTargetCodeForMemset(
SDValue Ops[] = { Chain, DAG.getValueType(AVT), InFlag };
Chain = DAG.getNode(X86ISD::REP_STOS, dl, Tys, Ops);
- if (TwoRepStos) {
- InFlag = Chain.getValue(1);
- Count = Size;
- EVT CVT = Count.getValueType();
- SDValue Left = DAG.getNode(ISD::AND, dl, CVT, Count,
- DAG.getConstant((AVT == MVT::i64) ? 7 : 3, dl,
- CVT));
- Chain = DAG.getCopyToReg(Chain, dl, (CVT == MVT::i64) ? X86::RCX : X86::ECX,
- Left, InFlag);
- InFlag = Chain.getValue(1);
- Tys = DAG.getVTList(MVT::Other, MVT::Glue);
- SDValue Ops[] = { Chain, DAG.getValueType(MVT::i8), InFlag };
- Chain = DAG.getNode(X86ISD::REP_STOS, dl, Tys, Ops);
- } else if (BytesLeft) {
+ if (BytesLeft) {
// Handle the last 1 - 7 bytes.
unsigned Offset = SizeVal - BytesLeft;
EVT AddrVT = Dst.getValueType();
@@ -195,6 +181,24 @@ SDValue X86SelectionDAGInfo::EmitTargetCodeForMemset(
return Chain;
}
+namespace {
+
+// Represents a cover of a buffer of SizeVal bytes with blocks of size
+// AVT, as well as how many bytes remain (BytesLeft is always smaller than
+// the block size).
+struct RepMovsRepeats {
+ RepMovsRepeats(const uint64_t SizeVal, const MVT& AVT) {
+ const unsigned UBytes = AVT.getSizeInBits() / 8;
+ Count = SizeVal / UBytes;
+ BytesLeft = SizeVal % UBytes;
+ }
+
+ unsigned Count;
+ unsigned BytesLeft;
+};
+
+} // namespace
+
SDValue X86SelectionDAGInfo::EmitTargetCodeForMemcpy(
SelectionDAG &DAG, const SDLoc &dl, SDValue Chain, SDValue Dst, SDValue Src,
SDValue Size, unsigned Align, bool isVolatile, bool AlwaysInline,
@@ -229,7 +233,12 @@ SDValue X86SelectionDAGInfo::EmitTargetCodeForMemcpy(
return SDValue();
MVT AVT;
- if (Align & 1)
+ if (Subtarget.hasERMSB())
+ // If the target has enhanced REPMOVSB, then it's at least as fast to use
+ // REP MOVSB instead of REP MOVS{W,D,Q}, and it avoids having to handle
+ // BytesLeft.
+ AVT = MVT::i8;
+ else if (Align & 1)
AVT = MVT::i8;
else if (Align & 2)
AVT = MVT::i16;
@@ -240,14 +249,18 @@ SDValue X86SelectionDAGInfo::EmitTargetCodeForMemcpy(
// QWORD aligned
AVT = Subtarget.is64Bit() ? MVT::i64 : MVT::i32;
- unsigned UBytes = AVT.getSizeInBits() / 8;
- unsigned CountVal = SizeVal / UBytes;
- SDValue Count = DAG.getIntPtrConstant(CountVal, dl);
- unsigned BytesLeft = SizeVal % UBytes;
+ RepMovsRepeats Repeats(SizeVal, AVT);
+ if (Repeats.BytesLeft > 0 &&
+ DAG.getMachineFunction().getFunction()->optForMinSize()) {
+ // When agressively optimizing for size, avoid generating the code to handle
+ // BytesLeft.
+ AVT = MVT::i8;
+ Repeats = RepMovsRepeats(SizeVal, AVT);
+ }
SDValue InFlag;
Chain = DAG.getCopyToReg(Chain, dl, Subtarget.is64Bit() ? X86::RCX : X86::ECX,
- Count, InFlag);
+ DAG.getIntPtrConstant(Repeats.Count, dl), InFlag);
InFlag = Chain.getValue(1);
Chain = DAG.getCopyToReg(Chain, dl, Subtarget.is64Bit() ? X86::RDI : X86::EDI,
Dst, InFlag);
@@ -262,9 +275,9 @@ SDValue X86SelectionDAGInfo::EmitTargetCodeForMemcpy(
SmallVector<SDValue, 4> Results;
Results.push_back(RepMovs);
- if (BytesLeft) {
+ if (Repeats.BytesLeft) {
// Handle the last 1 - 7 bytes.
- unsigned Offset = SizeVal - BytesLeft;
+ unsigned Offset = SizeVal - Repeats.BytesLeft;
EVT DstVT = Dst.getValueType();
EVT SrcVT = Src.getValueType();
EVT SizeVT = Size.getValueType();
@@ -275,7 +288,8 @@ SDValue X86SelectionDAGInfo::EmitTargetCodeForMemcpy(
DAG.getNode(ISD::ADD, dl, SrcVT, Src,
DAG.getConstant(Offset, dl,
SrcVT)),
- DAG.getConstant(BytesLeft, dl, SizeVT),
+ DAG.getConstant(Repeats.BytesLeft, dl,
+ SizeVT),
Align, isVolatile, AlwaysInline, false,
DstPtrInfo.getWithOffset(Offset),
SrcPtrInfo.getWithOffset(Offset)));